X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=regexec.c;h=464ceaf9e33ef8ec4c3e4884b10d48ec6f4a5c09;hb=b0b6bf2b21cef2068f6e0ff354c014823901afc7;hp=ebe7883b6091d1ee5533814aecd11ee102b63402;hpb=faf82a0b75a45f1e4dbb7ad8cecdfaf9a30a643d;p=p5sagit%2Fp5-mst-13.2.git diff --git a/regexec.c b/regexec.c index ebe7883..464ceaf 100644 --- a/regexec.c +++ b/regexec.c @@ -67,7 +67,8 @@ * **** Alterations to Henry's code are... **** - **** Copyright (c) 1991-2002, Larry Wall + **** Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, + **** 2000, 2001, 2002, 2003, by Larry Wall and others **** **** You may distribute under the terms of either the GNU General Public **** License or the Artistic License, as specified in the README file. @@ -86,6 +87,7 @@ #define RF_warned 2 /* warned about big count? */ #define RF_evaled 4 /* Did an EVAL with setting? */ #define RF_utf8 8 /* String contains multibyte chars? */ +#define RF_false 16 /* odd number of nested negatives */ #define UTF ((PL_reg_flags & RF_utf8) != 0) @@ -171,7 +173,7 @@ S_regcppush(pTHX_ I32 parenfloor) Perl_croak(aTHX_ "panic: paren_elems_to_push < 0"); #define REGCP_OTHER_ELEMS 6 - SSCHECK(paren_elems_to_push + REGCP_OTHER_ELEMS); + SSGROW(paren_elems_to_push + REGCP_OTHER_ELEMS); for (p = PL_regsize; p > parenfloor; p--) { /* REGCP_PARENS_ELEMS are pushed per pairs of parentheses. */ SSPUSHINT(PL_regendp[p]); @@ -544,7 +546,7 @@ Perl_re_intuit_start(pTHX_ regexp *prog, SV *sv, char *strpos, goto fail_finish; /* we may be pointing at the wrong string */ if (s && RX_MATCH_COPIED(prog)) - s = prog->subbeg + (s - SvPVX(sv)); + s = strbeg + (s - SvPVX(sv)); if (data) *data->scream_olds = s; } @@ -852,10 +854,6 @@ Perl_re_intuit_start(pTHX_ regexp *prog, SV *sv, char *strpos, char *startpos = strbeg; t = s; - if (prog->reganch & ROPT_UTF8) { - PL_regdata = prog->data; - PL_bostr = startpos; - } cache_re(prog); s = find_byclass(prog, prog->regstclass, s, endpos, startpos, 1); if (!s) { @@ -955,6 +953,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta I32 doevery = (prog->reganch & ROPT_SKIP) == 0; char *m; STRLEN ln; + STRLEN lnc; unsigned int c1; unsigned int c2; char *e; @@ -1010,10 +1009,12 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta } break; case EXACTF: - m = STRING(c); - ln = STR_LEN(c); + m = STRING(c); + ln = STR_LEN(c); /* length to match in octets/bytes */ + lnc = (I32) ln; /* length to match in characters */ if (UTF) { STRLEN ulen1, ulen2; + U8 *sm = (U8 *) m; U8 tmpbuf1[UTF8_MAXLEN_UCLC+1]; U8 tmpbuf2[UTF8_MAXLEN_UCLC+1]; @@ -1024,6 +1025,11 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta 0, ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); c2 = utf8n_to_uvchr(tmpbuf2, UTF8_MAXLEN_UCLC, 0, ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); + lnc = 0; + while (sm < ((U8 *) m + ln)) { + lnc++; + sm += UTF8SKIP(sm); + } } else { c1 = *(U8*)m; @@ -1031,12 +1037,13 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta } goto do_exactf; case EXACTFL: - m = STRING(c); - ln = STR_LEN(c); + m = STRING(c); + ln = STR_LEN(c); + lnc = (I32) ln; c1 = *(U8*)m; c2 = PL_fold_locale[c1]; do_exactf: - e = HOP3c(strend, -(I32)ln, s); + e = HOP3c(strend, -((I32)lnc), s); if (norun && e < s) e = s; /* Due to minlen logic of intuit() */ @@ -1059,6 +1066,8 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta STRLEN len, foldlen; if (c1 == c2) { + /* Upper and lower of 1st char are equal - + * probably not a "letter". */ while (s <= e) { c = utf8n_to_uvchr((U8*)s, UTF8_MAXLEN, &len, ckWARN(WARN_UTF8) ? @@ -1866,7 +1875,7 @@ Perl_regexec_flags(pTHX_ register regexp *prog, char *stringarg, register char * PL_multiline ? FBMrf_MULTILINE : 0))) ) { /* we may be pointing at the wrong string */ if ((flags & REXEC_SCREAM) && RX_MATCH_COPIED(prog)) - s = prog->subbeg + (s - SvPVX(sv)); + s = strbeg + (s - SvPVX(sv)); DEBUG_r( did_match = 1 ); if (HOPc(s, -back_max) > last1) { last1 = HOPc(s, -back_min); @@ -1955,7 +1964,7 @@ Perl_regexec_flags(pTHX_ register regexp *prog, char *stringarg, register char * last = scream_olds; /* Only one occurrence. */ /* we may be pointing at the wrong string */ else if (RX_MATCH_COPIED(prog)) - s = prog->subbeg + (s - SvPVX(sv)); + s = strbeg + (s - SvPVX(sv)); } else { STRLEN len; @@ -2838,6 +2847,7 @@ S_regmatch(pTHX_ regnode *prog) COP *ocurcop = PL_curcop; PAD *old_comppad; SV *ret; + struct regexp *oreg = PL_reg_re; n = ARG(scan); PL_op = (OP_4tree*)PL_regdata->data[n]; @@ -2970,8 +2980,10 @@ S_regmatch(pTHX_ regnode *prog) sw = SvTRUE(ret); logical = 0; } - else + else { sv_setsv(save_scalar(PL_replgv), ret); + cache_re(oreg); + } break; } case OPEN: @@ -3204,7 +3216,10 @@ S_regmatch(pTHX_ regnode *prog) "%*s already tried at this position...\n", REPORT_CODE_OFF+PL_regindent*2, "") ); - sayNO_SILENT; + if (PL_reg_flags & RF_false) + sayYES; + else + sayNO_SILENT; } PL_reg_poscache[o] |= (1<